background:Even intense exercise by astronauts cannot compensate for muscle atrophy caused by microgravity. Atrophy is caused, in part, by underlying mechanisms regulating calcium uptake. Recent studies have shown that exposure to spaceflight alters muscle calcium uptake. However, the molecular mechanisms driving these changes have not been well studied.
Researchers at the Ames Research Center investigated these mechanisms by applying machine learning (ML) to identify patterns in a dataset of mice exposed to microgravity. ML techniques are particularly effective at identifying patterns in complex biological data and are well-suited for astrobiology research, where small datasets are often combined to increase statistical power.
In the image above, NASA astronaut and Expedition 32 flight engineer Sunita Williams exercises on a weight-bearing treadmill aboard the ISS. Resistance training can counteract the negative health effects of microgravity on muscle atrophy, but new research from the Ames Research Center aims to identify biomarkers that could inform innovative countermeasures. We aim to understand the physiological mechanisms underlying this. This research was conducted as a funded project of NASA's Space Life Sciences Training Program at the Ames Research Center.
Investigation result: Machine learning analysis reveals molecular drivers for physiological changes in the sarcoendoplasmic reticulum of calcium channels (SERCA) pumps that lead to muscle alterations and muscle loss in spaceflight rodents. The ML model was created to identify proteins that can predict the resilience of an organism to microgravity with respect to calcium uptake in muscles. Specific proteins, Acyp1 and Rps7, were found to be the most predictive biomarkers associated with increased calcium uptake in fast twitch muscles.
impact: This study provided the first investigation into the use of ML on muscle calcium uptake when exposed to microgravity conditions. This research is part of NASA's Open Science Initiative in Accelerating Astrobiology, with reliance on ARC's Open Science Data Repository (OSDR) and Analysis Working Group, and the involvement of international research teams from the United States, Canada, Denmark, and the United States. I have proven my role. Australia. Notably, the lead author of this article is an undergraduate student at the University of California, Berkeley, and he is excited about the endless possibilities for NASA-Berkeley collaboration in life sciences research with the soon-to-be-built Berkeley Space Center at the NASA Research Park. This is something that has been proven.
Reference: Li, K., Desai, R., Scott, R., Steele, J., Sanders, L., Cotess, S. Multi-omic signatures of muscle responses to spaceflight in mice with explainable machine learning. is identified. npj microgravity 9, 90 (December 2023).
